linkfox-multimodal-extract-attributes
Warn
Audited by Snyk on Apr 22, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill explicitly ingests and analyzes product images supplied via public image URLs (see "Image accessibility: Product image URLs must be publicly accessible" in SKILL.md, the refResultData/imageUrl fields in references/api.md, and the example in scripts/multimodal_extract_attributes.py), so untrusted third‑party images are fetched and their content directly influences the model's analysis and outputs.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata